Research map / Label-efficient and robust learning / Domain adaptation and generalization
Dual-Bridging With Adversarial Noise Generation for Domain Adaptive rPPG Estimation
Jingda Du, Si-Qi Liu, Bochao Zhang, Pong C. Yuen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply dual-bridging noise adaptation | rPPG estimation model · MMSE-HR task-independent | MAE: 1.20 -> 0.85 | Improved |
| Apply dual-bridging noise adaptation | rPPG estimation model · UBFC-rPPG participant-independent | MAE: 0.41 -> 0.16 | Improved |
| Apply dual-bridging noise adaptation | rPPG estimation model · MMSE-HR → PURE | MAE: 1.27 -> 1.10 | Improved |
| Apply dual-bridging noise adaptation | rPPG estimation model · PURE → MMSE-HR | MAE: 2.32 -> 1.71 | Improved |
| Apply dual-bridging noise adaptation | rPPG estimation model · PURE → UBFC-rPPG | MAE: 0.74 -> 0.58 | Improved |
| Add noise reducer ↔ domain classifier (ablation) | dual-bridging rPPG model · MMSE-HR → PURE | MAE: 2.96 -> 2.13 | Improved |
| Add noise reducer ↔ domain classifier (ablation) | dual-bridging rPPG model · PURE → MMSE-HR | MAE: 2.09 -> 20.27 | Hurt |
| Add generator ↔ domain classifier (ablation) | model with noise reducer ↔ domain classifier · MMSE-HR → PURE | MAE: 2.13 -> 1.66 | Improved |
| Add generator ↔ domain classifier (ablation) | model with noise reducer ↔ domain classifier · PURE → MMSE-HR | MAE: 20.27 -> 1.88 | Improved |
| Add generator conditioned on noise reducer (ablation) | model with NR ↔ D and G ↔ D · MMSE-HR → PURE | MAE: 1.66 -> 1.13 | Improved |
| Add generator conditioned on noise reducer (ablation) | model with NR ↔ D and G ↔ D · PURE → MMSE-HR | MAE: 1.88 -> 1.71 | Improved |
| Add hard noise pattern mining (ablation) | dual-bridging model with adversarial noise generation · MMSE-HR → PURE | MAE: 1.13 -> 1.10 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Dual-GAN — Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement (CVPR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological Measurement (CVPR 2021 · similarity 0.91)
- Augmentation of rPPG Benchmark Datasets: Learning to Remove and Embed rPPG Signals via Double Cycle Consistent Learning from Unpaired Facial Videos (ECCV 2022 · similarity 0.89)
- Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos (AAAI 2023 · similarity 0.89)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.87)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
